From: Dan Williams <[EMAIL PROTECTED]>
Each stripe has three flag variables to reflect the state of operations
(pending, ack, and complete).
-pending: set to request servicing in raid5_run_ops
-ack: set to reflect that raid5_runs_ops has seen this request
-complete: set when the operation is complete and it is ok for handle_stripe5
to clear 'pending' and 'ack'.
Signed-off-by: Dan Williams <[EMAIL PROTECTED]>
---
drivers/md/raid5.c | 65 +++++++++++++++++++++++++++++++++++++++++++++-------
1 files changed, 56 insertions(+), 9 deletions(-)
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index e70ee17..2c74f9b 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -126,6 +126,7 @@ static void __release_stripe(raid5_conf_t *conf, struct
stripe_head *sh)
}
md_wakeup_thread(conf->mddev->thread);
} else {
+ BUG_ON(sh->ops.pending);
if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE,
&sh->state)) {
atomic_dec(&conf->preread_active_stripes);
if (atomic_read(&conf->preread_active_stripes)
< IO_THRESHOLD)
@@ -225,7 +226,8 @@ static void init_stripe(struct stripe_head *sh, sector_t
sector, int pd_idx, int
BUG_ON(atomic_read(&sh->count) != 0);
BUG_ON(test_bit(STRIPE_HANDLE, &sh->state));
-
+ BUG_ON(sh->ops.pending || sh->ops.ack || sh->ops.complete);
+
CHECK_DEVLOCK();
PRINTK("init_stripe called, stripe %llu\n",
(unsigned long long)sh->sector);
@@ -241,11 +243,11 @@ static void init_stripe(struct stripe_head *sh, sector_t
sector, int pd_idx, int
for (i = sh->disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
- if (dev->toread || dev->towrite || dev->written ||
+ if (dev->toread || dev->read || dev->towrite || dev->written ||
test_bit(R5_LOCKED, &dev->flags)) {
- printk("sector=%llx i=%d %p %p %p %d\n",
+ printk("sector=%llx i=%d %p %p %p %p %d\n",
(unsigned long long)sh->sector, i, dev->toread,
- dev->towrite, dev->written,
+ dev->read, dev->towrite, dev->written,
test_bit(R5_LOCKED, &dev->flags));
BUG();
}
@@ -325,6 +327,43 @@ static struct stripe_head *get_active_stripe(raid5_conf_t
*conf, sector_t sector
return sh;
}
+/* check_op() ensures that we only dequeue an operation once */
+#define check_op(op) do {\
+ if (test_bit(op, &sh->ops.pending) &&\
+ !test_bit(op, &sh->ops.complete)) {\
+ if (test_and_set_bit(op, &sh->ops.ack))\
+ clear_bit(op, &pending);\
+ else\
+ ack++;\
+ } else\
+ clear_bit(op, &pending);\
+} while(0)
+
+/* find new work to run, do not resubmit work that is already
+ * in flight
+ */
+static unsigned long get_stripe_work(struct stripe_head *sh)
+{
+ unsigned long pending;
+ int ack = 0;
+
+ pending = sh->ops.pending;
+
+ check_op(STRIPE_OP_BIOFILL);
+ check_op(STRIPE_OP_COMPUTE_BLK);
+ check_op(STRIPE_OP_PREXOR);
+ check_op(STRIPE_OP_BIODRAIN);
+ check_op(STRIPE_OP_POSTXOR);
+ check_op(STRIPE_OP_CHECK);
+ if (test_and_clear_bit(STRIPE_OP_IO, &sh->ops.pending))
+ ack++;
+
+ sh->ops.count -= ack;
+ BUG_ON(sh->ops.count < 0);
+
+ return pending;
+}
+
static int
raid5_end_read_request(struct bio * bi, unsigned int bytes_done, int error);
static int
@@ -1859,7 +1898,6 @@ static int stripe_to_pdidx(sector_t stripe, raid5_conf_t
*conf, int disks)
* schedule a write of some buffers
* return confirmation of parity correctness
*
- * Parity calculations are done inside the stripe lock
* buffers are taken off read_list or write_list, and bh_cache buffers
* get BH_Lock set before the stripe lock is released.
*
@@ -1877,10 +1915,11 @@ static void handle_stripe5(struct stripe_head *sh)
int non_overwrite = 0;
int failed_num=0;
struct r5dev *dev;
+ unsigned long pending=0;
- PRINTK("handling stripe %llu, cnt=%d, pd_idx=%d\n",
- (unsigned long long)sh->sector, atomic_read(&sh->count),
- sh->pd_idx);
+ PRINTK("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d
ops=%lx:%lx:%lx\n",
+ (unsigned long long)sh->sector, sh->state,
atomic_read(&sh->count),
+ sh->pd_idx, sh->ops.pending, sh->ops.ack, sh->ops.complete);
spin_lock(&sh->lock);
clear_bit(STRIPE_HANDLE, &sh->state);
@@ -2330,8 +2369,14 @@ static void handle_stripe5(struct stripe_head *sh)
}
}
+ if (sh->ops.count)
+ pending = get_stripe_work(sh);
+
spin_unlock(&sh->lock);
+ if (pending)
+ raid5_run_ops(sh, pending);
+
while ((bi=return_bi)) {
int bytes = bi->bi_size;
@@ -3712,8 +3757,10 @@ static void raid5d (mddev_t *mddev)
handled++;
}
- if (list_empty(&conf->handle_list))
+ if (list_empty(&conf->handle_list)) {
+ async_tx_issue_pending_all();
break;
+ }
first = conf->handle_list.next;
sh = list_entry(first, struct stripe_head, lru);
-
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
